Advancing diagnostic precision: Unveiling sensitization relationships between cat, dog, and horse allergen molecules.

BACKGROUND: Recent advancements in molecular diagnostics have unveiled a multitude of allergen molecules (AMs) associated with animal sensitizations, revealing significant cross- and co-sensitization patterns among these seemingly distinct allergens. METHOD: We investigated the sensitization profiles of 120 children, sensitized to at least one of the 14 AMs from cat, dog, or horse using the Alex test, employing correlations and hierarchical clusters to explore relationship between sensitizations. RESULTS: Sensitizations to Fel d 1, Can f 4/5, and Equ c 4 differ from other cat, dog, and horse AM sensitizations, suggesting they may represent genuine sensitizations for their respective animals. High correlations were observed among various AMs, including lipocalins (Can f 1/2/6, Fel d 4/7, and Equ c 1), serum albumins (Fel d 2, Can f 3, and Equ c 3), and uteroglobins (Fel d 1 and Can f_Fd1). Hierarchical clustering of sensitizations identified two similarity clusters and one dissimilarity cluster, providing an estimation of the likelihood of cross-reactivity. Additionally, our method facilitated speculation regarding cross-, co-, or genuine sensitization. Moreover, we noted a potential increase in the number and level of sensitized animal AMs concurrent with increased sensitization to other aeroallergens with advancing age. No significant difference was detected for the presence or absence of various types of allergic comorbidities. CONCLUSION: Correlations and hierarchical clustering can unveil the extent and magnitude of cross-, co-, and genuine sensitization relationships among animal AMs. These insights can be leveraged to enhance artificial intelligence algorithms, improving diagnostic accuracy through the integration of other measures of sensitization.

Multitask Learning for Activity Detection in Neovascular Age-Related Macular Degeneration.

Purpose: The purpose of this study was to provide a comparison of performance and explainability of a multitask convolutional deep neuronal network to single-task networks for activity detection in neovascular age-related macular degeneration (nAMD). Methods: From 70 patients (46 women and 24 men) who attended the University Eye Hospital Tübingen, 3762 optical coherence tomography B-scans (right eye = 2011 and left eye = 1751) were acquired with Heidelberg Spectralis, Heidelberg, Germany. B-scans were graded by a retina specialist and an ophthalmology resident, and then used to develop a multitask deep learning model to predict disease activity in neovascular age-related macular degeneration along with the presence of sub- and intraretinal fluid. We used performance metrics for comparison to single-task networks and visualized the deep neural network (DNN)-based decision with t-distributed stochastic neighbor embedding and clinically validated saliency mapping techniques. Results: The multitask model surpassed single-task networks in accuracy for activity detection (94.2% vs. 91.2%). The area under the curve of the receiver operating curve was 0.984 for the multitask model versus 0.974 for the single-task model. Furthermore, compared to single-task networks, visualizations via t-distributed stochastic neighbor embedding and saliency maps highlighted that multitask networks' decisions for activity detection in neovascular age-related macular degeneration were highly consistent with the presence of both sub- and intraretinal fluid. Conclusions: Multitask learning increases the performance of neuronal networks for predicting disease activity, while providing clinicians with an easily accessible decision control, which resembles human reasoning. Translational Relevance: By improving nAMD activity detection performance and transparency of automated decisions, multitask DNNs can support the translation of machine learning research into clinical decision support systems for nAMD activity detection.

Clinical validation of saliency maps for understanding deep neural networks in ophthalmology.

Deep neural networks (DNNs) have achieved physician-level accuracy on many imaging-based medical diagnostic tasks, for example classification of retinal images in ophthalmology. However, their decision mechanisms are often considered impenetrable leading to a lack of trust by clinicians and patients. To alleviate this issue, a range of explanation methods have been proposed to expose the inner workings of DNNs leading to their decisions. For imaging-based tasks, this is often achieved via saliency maps. The quality of these maps are typically evaluated via perturbation analysis without experts involved. To facilitate the adoption and success of such automated systems, however, it is crucial to validate saliency maps against clinicians. In this study, we used three different network architectures and developed ensembles of DNNs to detect diabetic retinopathy and neovascular age-related macular degeneration from retinal fundus images and optical coherence tomography scans, respectively. We used a variety of explanation methods and obtained a comprehensive set of saliency maps for explaining the ensemble-based diagnostic decisions. Then, we systematically validated saliency maps against clinicians through two main analyses - a direct comparison of saliency maps with the expert annotations of disease-specific pathologies and perturbation analyses using also expert annotations as saliency maps. We found the choice of DNN architecture and explanation method to significantly influence the quality of saliency maps. Guided Backprop showed consistently good performance across disease scenarios and DNN architectures, suggesting that it provides a suitable starting point for explaining the decisions of DNNs on retinal images.

Clinical profile of delusional disorder and its subtypes: a descriptive study from Turkey.

The fact that delusional disorder (DD) received minimal research attention indicates the need for descriptive studies that will better delineate the clinical and socio-demographic characteristics of DD. We conducted a chart review descriptive study in a tertiary hospital from Turkey. A total of 99 cases of DD were identified through hospital registry system. 57 were male (57.6%), and mean age at first admission was 49.34±13.49. The most common type of DD was persecutory (36.4%), followed by jealous type (28.3%), mixed type (18.2%), and somatic type (16.2%). Jealous type DD patients were more likely to be married, and mixed type DD patients were more likely to be divorced. The presence of hallucinations was significantly associated with history of hospitalization. About one-tenth of the patients had a family history of psychotic spectrum disorder. Comorbid depressive disorder was present in 42.9% of the patients, whereas only 9.2% had comorbid anxiety disorder. Depressive disorder comorbidity in DD seems to be associated with continued treatment for longer periods of time in psychiatry services. While most of our data were comparable with the literature on DD, our divergent findings like higher rates of male patients and jealous type of the disorder might be attributed to the cultural and geographical factors. This situation points out that future research with larger populations and from different regions would contribute to better understanding of clinical and socio-demographical characteristics of delusional disorder.

Expert-validated estimation of diagnostic uncertainty for deep neural networks in diabetic retinopathy detection.

Deep learning-based systems can achieve a diagnostic performance comparable to physicians in a variety of medical use cases including the diagnosis of diabetic retinopathy. To be useful in clinical practice, it is necessary to have well calibrated measures of the uncertainty with which these systems report their decisions. However, deep neural networks (DNNs) are being often overconfident in their predictions, and are not amenable to a straightforward probabilistic treatment. Here, we describe an intuitive framework based on test-time data augmentation for quantifying the diagnostic uncertainty of a state-of-the-art DNN for diagnosing diabetic retinopathy. We show that the derived measure of uncertainty is well-calibrated and that experienced physicians likewise find cases with uncertain diagnosis difficult to evaluate. This paves the way for an integrated treatment of uncertainty in DNN-based diagnostic systems.